Matches in SemOpenAlex for { <https://semopenalex.org/work/W2890124293> ?p ?o ?g. }
Showing items 1 to 94 of
94
with 100 items per page.
- W2890124293 endingPage "20" @default.
- W2890124293 startingPage "14" @default.
- W2890124293 abstract "Convolutional Neural Networks (CNNs) have achieved great success for action recognition. Technically, extracting effective long-range temporal dynamics is critical for such temporal tasks. This paper proposes a temporal stochastic linear encoding (TSLE) to construct the global video representations for action recognition, which can be embedded inside of CNN as a layer. The advantages of temporal stochastic linear encoding networks (TSLEN) are: (a) Compared with algorithms focusing on the short-term motions it can implement an easy yet robust manipulation of long range temporal clues. (b) We propose an arbitrarily directional motion boundary (ADMB) unit, which can save the training time and hard disk space. (c) The proposed TSLE unit maps the highly-dimensional videos to the compact spatio-temporal representations. On the efficiency and recognition accuracy experimental results demonstrate that the proposed TSLENs achieve competitive performance among the effective algorithms. • The proposed TSLE network can implement an easy yet robust manipulation of long range temporal clues. • We propose an arbitrarily directional motion boundary (ADMB) units embodied inside of the CNN, which can save the training time and hard disk space. • We train the proposed TSLE networks on the large-scale Kinetics dataset, and with the obtained model we train the models on the UCF101 and HMDB51. • The proposed TSLE networks map a highly-dimensional video to a compact spatio-temporal representation." @default.
- W2890124293 created "2018-09-27" @default.
- W2890124293 creator A5015887120 @default.
- W2890124293 creator A5027627900 @default.
- W2890124293 creator A5060804553 @default.
- W2890124293 creator A5088347883 @default.
- W2890124293 date "2019-02-01" @default.
- W2890124293 modified "2023-10-03" @default.
- W2890124293 title "Temporal stochastic linear encoding networks" @default.
- W2890124293 cites W1489737693 @default.
- W2890124293 cites W1686810756 @default.
- W2890124293 cites W1983364832 @default.
- W2890124293 cites W2068611653 @default.
- W2890124293 cites W2097117768 @default.
- W2890124293 cites W2139594308 @default.
- W2890124293 cites W2156303437 @default.
- W2890124293 cites W2176316098 @default.
- W2890124293 cites W2193384753 @default.
- W2890124293 cites W2235034809 @default.
- W2890124293 cites W2471775118 @default.
- W2890124293 cites W2508429489 @default.
- W2890124293 cites W2612569699 @default.
- W2890124293 cites W2618530766 @default.
- W2890124293 cites W2962889000 @default.
- W2890124293 cites W787785461 @default.
- W2890124293 doi "https://doi.org/10.1016/j.image.2018.09.001" @default.
- W2890124293 hasPublicationYear "2019" @default.
- W2890124293 type Work @default.
- W2890124293 sameAs 2890124293 @default.
- W2890124293 citedByCount "0" @default.
- W2890124293 crossrefType "journal-article" @default.
- W2890124293 hasAuthorship W2890124293A5015887120 @default.
- W2890124293 hasAuthorship W2890124293A5027627900 @default.
- W2890124293 hasAuthorship W2890124293A5060804553 @default.
- W2890124293 hasAuthorship W2890124293A5088347883 @default.
- W2890124293 hasConcept C104114177 @default.
- W2890124293 hasConcept C11413529 @default.
- W2890124293 hasConcept C125411270 @default.
- W2890124293 hasConcept C134306372 @default.
- W2890124293 hasConcept C153180895 @default.
- W2890124293 hasConcept C154945302 @default.
- W2890124293 hasConcept C159985019 @default.
- W2890124293 hasConcept C17744445 @default.
- W2890124293 hasConcept C192562407 @default.
- W2890124293 hasConcept C199360897 @default.
- W2890124293 hasConcept C199539241 @default.
- W2890124293 hasConcept C204323151 @default.
- W2890124293 hasConcept C2776359362 @default.
- W2890124293 hasConcept C2780801425 @default.
- W2890124293 hasConcept C33923547 @default.
- W2890124293 hasConcept C41008148 @default.
- W2890124293 hasConcept C62354387 @default.
- W2890124293 hasConcept C81363708 @default.
- W2890124293 hasConcept C94625758 @default.
- W2890124293 hasConceptScore W2890124293C104114177 @default.
- W2890124293 hasConceptScore W2890124293C11413529 @default.
- W2890124293 hasConceptScore W2890124293C125411270 @default.
- W2890124293 hasConceptScore W2890124293C134306372 @default.
- W2890124293 hasConceptScore W2890124293C153180895 @default.
- W2890124293 hasConceptScore W2890124293C154945302 @default.
- W2890124293 hasConceptScore W2890124293C159985019 @default.
- W2890124293 hasConceptScore W2890124293C17744445 @default.
- W2890124293 hasConceptScore W2890124293C192562407 @default.
- W2890124293 hasConceptScore W2890124293C199360897 @default.
- W2890124293 hasConceptScore W2890124293C199539241 @default.
- W2890124293 hasConceptScore W2890124293C204323151 @default.
- W2890124293 hasConceptScore W2890124293C2776359362 @default.
- W2890124293 hasConceptScore W2890124293C2780801425 @default.
- W2890124293 hasConceptScore W2890124293C33923547 @default.
- W2890124293 hasConceptScore W2890124293C41008148 @default.
- W2890124293 hasConceptScore W2890124293C62354387 @default.
- W2890124293 hasConceptScore W2890124293C81363708 @default.
- W2890124293 hasConceptScore W2890124293C94625758 @default.
- W2890124293 hasFunder F4320321001 @default.
- W2890124293 hasLocation W28901242931 @default.
- W2890124293 hasOpenAccess W2890124293 @default.
- W2890124293 hasPrimaryLocation W28901242931 @default.
- W2890124293 hasRelatedWork W2175746458 @default.
- W2890124293 hasRelatedWork W2738221750 @default.
- W2890124293 hasRelatedWork W2760085659 @default.
- W2890124293 hasRelatedWork W2773521834 @default.
- W2890124293 hasRelatedWork W2912288872 @default.
- W2890124293 hasRelatedWork W2947554386 @default.
- W2890124293 hasRelatedWork W3081496756 @default.
- W2890124293 hasRelatedWork W3086857729 @default.
- W2890124293 hasRelatedWork W3093612317 @default.
- W2890124293 hasRelatedWork W564581980 @default.
- W2890124293 hasVolume "70" @default.
- W2890124293 isParatext "false" @default.
- W2890124293 isRetracted "false" @default.
- W2890124293 magId "2890124293" @default.
- W2890124293 workType "article" @default.